arXiv AI
World Action Critic (WAC) Model: Joint Foresight and Criticism for Policy Learning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 20
DA-WAM: Decision-Aligned Future Latents for Driving World Models
DA‑WAM is a framework that integrates predictive representation learning, action‑conditioned future modeling, and trajectory scoring into a single decision‑making objective for autonomous driving. It uses an online encoder with a stable momentum target to keep future representations aligned with the driving task, generating a distinct future latent for each trajectory candidate. A future‑latent‑conditioned scorer evaluates these latents, with expert‑matched trajectories supervised by observed futures and safety‑critical hard negatives providing additional guidance, achieving state‑of‑the‑art results on NAVSIM‑v1 and NAVSIM‑v2.
arXiv Machine Learning
Oct 9
PlanWAM: Planning-Shaped Future Representations for End-to-End Autonomous Driving
PlanWAM introduces a Planning‑Shaped World Action Model that tailors future‑state representations to be most useful for trajectory planning in end‑to‑end autonomous driving. It compresses historical observations with a Temporal Register Pyramid, shapes a future latent representation using a privileged posterior branch guided by planning objectives, and distills this into a prior branch that predicts the representation from history alone. The resulting foresighted planning context yields state‑of‑the‑art performance on NAVSIM and HUGSIM benchmarks.
arXiv Computer Vision
Aug 25
ReWorld: Representation Learning for World Action Models
arXiv:2606.27504v2 Announce Type: replace Abstract: World Action Models (WAMs) unify future environment prediction with action generation for autonomous driving, yet existing approaches optimize only...
arXiv AI
4d ago
Beyond Action Prediction: Learning Search-Free Planning in Latent Space
The paper introduces Hindsight Inverse JEPA Planning (HIJP), a search‑free framework that replaces costly online action sequence optimization with a goal‑conditioned inverse model. HIJP trains by relabeling future observations as goals, providing action supervision across multiple horizons and shaping visual representations. The method also aligns predicted actions with a latent predictor model to enforce action‑transition consistency, achieving high success rates and significant speedups on visual control tasks.
arXiv Computer Vision
Sep 23
ForeDrive: Foresight-Guided End-to-End Autonomous Driving with a Planning-Relevant Latent World Model
ForeDrive introduces a planning-relevant latent world model that is asymmetrically coupled to a Diffusion Transformer planner. The model learns multi‑horizon latent futures with a JEPA‑style world model, while planning gradients update the shared encoder and stop‑gradient routing trains the predictor with forecasting losses only. Gated visual fusion, future‑status injection, and Trajectory‑Adaptive Bias are used to guide trajectory generation without overriding current observations, achieving high performance on NAVSIM benchmarks using only front‑view images and pure imitation learning.
arXiv Computer Vision
Oct 2
FutureWorlds: Learning Robotic World Models from Alternative Futures
FutureWorlds is a framework that learns robotic world models by generating alternative future predictions and using them as learning signals. It combines candidate construction, history maintenance, and learning from relative quality through a multimodal discrete autoregressive model and diverse beam search. The MemSPO algorithm further optimizes the world model by converting video trajectory rewards into group-relative advantages, leading to significant improvements in LPIPS scores across RT-1, BridgeV2, and RoboCasa datasets.